Harvesting Knowledge from Social Networks: Extracting Typed Relationships among Entities
Download as PPTX, PDF2 likes639 views
The document presents a methodology for extracting typed relationships among entities from unstructured social media data, such as tweets and Facebook posts. It outlines an analysis pipeline consisting of preprocessing, entity extraction, relationship extraction, aggregation, and typing, demonstrating this with practical examples. The findings suggest that while extracting relevant relationships is feasible, challenges such as poor entity typing and n-ary relation extraction remain.
Harvesting Knowledge from Social Networks: Extracting Typed Relationships among Entities
- 1. Harvesting Knowledge from Social Networks: Extracting Typed Relationships among Entities Andrea Caielli, Marco Brambilla, Stefano Ceri, Florian Daniel marco.brambilla@polimi.it marcobrambi SoWeMine Workshop @ ICWE 2017, Rome, Italy
- 2. Agenda (1)Context (2)Objectives (3)Method (4)Experiments and Validation (5)Visualization and Exploration (6)Conclusions
- 3. (1) Context
- 4. Ontology is the philosophical study of the nature of being, becoming, existence or reality and the basic categories of being and their relations.
- 5. Formalizing new knowledge is hard Only high frequency emerges The long tail challenge
- 6. Sourcing the Long Tail Famous Emerging …
- 8. Objective Extraction of relationships among entities Reconstruct a typed graph of entities & relationships Represent the knowledge contained in social data No need for a-priori domain knowledge
- 9. Knowledge Enrichment Setting HF Entity1 HF Entity5 HF Entity2 HF Entity4 HF Entity3 LF Entity1 ?? LF Entity2 LF Entity4 LF Entity3 ?? High Frequency Entities Low Frequency Entities ?? ?? ???? ?? Type1 Type11 Type2 Type111 Instances Types <<instanceof>> <<instanceof>> <<instanceof>> <<instanceof>> <<instanceof>> <<instanceof>> ?? ?? ?? ?? ?? Seed Entity Seed Type Type of interest Legend Expert inputs Enrichment problems Property2 Relations HF - LF entities Relations LF - LF entities Typing of LF entities Extraction of new LF entities Property1 ?? ?? ?? Finding attribute values
- 12. Challenge and Innovation Highly unstructured social data (tweets and Facebook posts) No reliable grammar structures
- 13. (3) Method
- 14. Analysis Pipeline (0) Preprocessing (1) Entity Extraction (2) Relationship Extraction (3) Relationship Aggregation (4) Relationship Typing (1) Evolution of work presented in: M. Brambilla, S. Ceri, E. Della Valle, R. Volonterio, and F. Acero Salazar. “Extracting Emerging Knowledge from Social Media”, WWW 2017.
- 15. Pipeline Summary
- 16. (0) Preprocessing Text cleaning and enrichment + Traditional text preprocessing (stemming, …)
- 17. (1) Entity Extraction Entity identification and semantic typing Exploiting: Stanford CoreNLP NER Dandelion API
- 18. (2) Relationship Extraction Baseline with Stanford OpenIE for triple extraction: Several issues: - Meaningless relations - Wrong relations - Multiple relations
- 19. (3) Relationship Aggregation Sails fans. Season 2 airs on May 24th on History on D Stv Jag Comms Too many answers for the same question! Empirical rules {"entity1":"Season 2", "relationship":"air on", "entity2":"May 24th"}
- 20. (4) Relationship Typing (A): Synonyms Exploiting synsets based on WordNet 3.1
- 21. (4) Relationship Typing (B): Matching Types
- 22. (4) Relationship Typing (C): Linguistics Based on VerbNet Groupings of verbs based on syntactic and semantic properties
- 24. (4) Validation
- 25. Experiments TV Series: Black Salis, Teen Wolf, Vikings Milan Fashion Week Rugby games
- 26. Domains and quality of results - summary
- 27. Relationships and Verb Classes
- 28. Example: Teen Wolf 0 100 200 300 400 500 600 700 800 Occurrences Teen Wolf Synonyms Classes
- 29. Example: Teen Wolf 0 100 200 300 400 500 600 700 800 Occurrences Teen Wolf Synonyms Classes OCCURRENCES TEEN WOLF VERBNET CLASSES
- 30. Overall Quality Indexes of Entity and Relationships Extraction
- 32. Motivation Resulting semantic models extremely large and hard to interpret Example: Black Sails collection, containing 1243 entities and 2025 relations.
- 40. (6) Conclusions
- 41. Conclusions Extraction of relevant emerging relationships feasible even in case of extremely unstructured and informal content (social media) Still a long way to perfect extraction: •N-ary relations •Time-dependency •Poor typing of entities in ontologies
- 42. THANKS! QUESTIONS? Andrea Caielli, Marco Brambilla, Stefano Ceri, Florian Daniel Harvesting Knowledge from Social Networks: Extracting Typed Relationships among Entities Marco Brambilla @marcobrambi marco.brambilla@polimi.it http://datascience.deib.polimi.it http://home.deib.polimi.it/marcobrambi